Protect, show, attend and tell: Empowering image captioning models with ownership protection.
Jian Han LimChee Seng ChanKamWoh NgLixin FanQiang YangPublished in: Pattern Recognit. (2022)
Keyphrases
- image analysis
- image data
- input image
- image features
- single image
- multiscale
- template matching
- image pixels
- random fields
- edge detection
- segmentation method
- image segmentation
- surface model
- parametric models
- vector field
- image structure
- image classification
- image retrieval
- object models
- image statistics
- visual effects
- lighting conditions
- region of interest
- test images
- image representation
- video sequences
- image collections
- bayesian framework
- pixel values
- image content
- image regions
- data protection